Detail
Rekomendasi
v1.0
Might-Mixes pXL-RoughCut

Might-Mixes pXL-RoughCut

5.8K
29
0

(Copied from Civitai)Regarding PonyXL merges <-- in the frontA Mix/Merge of some of many ???? random artist styles loras around the site. So results will vary depending on prompts usage - they all was trained on some form of PonyXL (itself or train/merged from it) so if your not using any form of PonyXL then these wont work that well - I dont remember all the styles or what their strengths are. But its so I dont need to download so many lora stylesQuality prompts for PXL - are some form of score_9,score_8_up,score_7_up,score_6_up, or some say add (score_3_up, score_4_up, score_5_up), in NEG - mess around with them. Neg prompts should only be something specific I think instead of a mountains of textmay need a XL VAE - Images must be - at or past 1024x1024 or 832x1024 - Sampling steps past 30 - is what I usually do - with some hi-rez fix and low denoise

Lihat terjemahan

Rating dan Ulasan

5.0 /5
0 rating

Belum menerima penilaian atau komentar yang cukup

avatar
avatar_frame
Pengumuman
2024-05-06
Memposting model
2025-01-08
Perbarui informasi model
Detail model
Jenis
Checkpoint
Waktu publikasi
2024-05-06
Model Dasar
SDXL 1.0
Perkenalan versi

(Copied from Civitai)Regarding PonyXL merges <-- in the frontA Mix/Merge of some of many ???? random artist styles loras around the site. So results will vary depending on prompts usage - they all was trained on some form of PonyXL (itself or train/merged from it) so if your not using any form of PonyXL then these wont work that well - I dont remember all the styles or what their strengths are. But its so I dont need to download so many lora stylesQuality prompts for PXL - are some form of score_9,score_8_up,score_7_up,score_6_up, or some say add (score_3_up, score_4_up, score_5_up), in NEG - mess around with them. Neg prompts should only be something specific I think instead of a mountains of textmay need a XL VAE - Images must be - at or past 1024x1024 or 832x1024 - Sampling steps past 30 - is what I usually do - with some hi-rez fix and low denoise

Cakupan Lisensi
Model Source: civitai

1. Hak untuk model yang diposting ulang adalah milik pembuat aslinya.

2. Pencipta asli yang ingin mengklaim model harap hubungi staf SeaArt AI melalui saluran resmi. Klik untuk mengklaim

Cakupan Lisensi Penciptaan
Gambar Online
Melakukan Penggabungan
Izinkan Unduhan
Lisensi Komersial
Gambar yang dihasilkan dapat dijual atau digunakan untuk tujuan komersial
Izinkan model dijual kembali atau dijual setelah penggabungan
QR Code
Unduh SeaArt App
Lanjutkan perjalanan kreasi AI Anda di perangkat mobile